Push model using huggingface_hub.

README.md

@@ -8,11 +8,11 @@ tags:
 metrics:
 - accuracy
 widget:
-- text: a red and yellow salon sign hangs above a nice street
 - text: several surfers one happy girl diving off her board
-- text: a ugly cat is laying on a laptop computer
-- text: he may not be the best man but he does make some good food
-- text: small number of horses with jockeys in a race on a track
+- text: a man in his yard on a motorcycle where there is dead grass
+- text: here is the wall of an interesting building with a clock built in to it
+- text: a polar bear with his chin raised lies on a nice rock
+- text: the awesome building with the clock is beset by a perfect sky
 pipeline_tag: text-classification
 inference: true
 base_model: sentence-transformers/paraphrase-mpnet-base-v2
@@ -46,10 +46,10 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
 ### Model Labels
-| Label | Examples                                                                                                                                                                                                                                                           |
-|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| 0     | <ul><li>'a man rides his surfboard through too shallow water'</li><li>'a cat is sleeping outside an ugly building near a door'</li><li>'a horrific view of two stupid people on the beach under a umbrella'</li></ul>                                              |
-| 1     | <ul><li>'a nice person uses the efficient laptop to monitor security in this amazing building'</li><li>'the awesome building with the clock is beset by a perfect sky'</li><li>'three different traffic welcome signs with a building in the background'</li></ul> |
+| Label | Examples                                                                                                                                                                                                                                |
+|:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 0     | <ul><li>'a shy girl is hiding herself from the hard rain under a white umbrella'</li><li>'the little kid got caught playing the video game without permission'</li><li>'a drunk guy rides a surfboard in a created wave pool'</li></ul> |
+| 1     | <ul><li>'a cute cate is sitting in an office chair in a nice room'</li><li>'a nice person on a bike on a most beautiful street'</li><li>'a display of a great variety of donuts at a store'</li></ul>                                   |
 
 ## Uses
 
@@ -69,7 +69,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("setfit_model_id")
 # Run inference
-preds = model("a ugly cat is laying on a laptop computer")
+preds = model("several surfers one happy girl diving off her board")
 ```
 
 <!--
@@ -101,16 +101,16 @@ preds = model("a ugly cat is laying on a laptop computer")
 ### Training Set Metrics
 | Training set | Min | Median  | Max |
 |:-------------|:----|:--------|:----|
-| Word count   | 9   | 11.5625 | 14  |
+| Word count   | 8   | 11.8906 | 36  |
 
 | Label | Training Sample Count |
 |:------|:----------------------|
-| 0     | 8                     |
-| 1     | 8                     |
+| 0     | 32                    |
+| 1     | 32                    |
 
 ### Training Hyperparameters
 - batch_size: (16, 16)
-- num_epochs: (4, 4)
+- num_epochs: (3, 3)
 - max_steps: -1
 - sampling_strategy: oversampling
 - body_learning_rate: (2e-05, 1e-05)
@@ -128,7 +128,14 @@ preds = model("a ugly cat is laying on a laptop computer")
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.1111 | 1    | 0.2801        | -               |
+| 0.0076 | 1    | 0.3787        | -               |
+| 0.3788 | 50   | 0.011         | -               |
+| 0.7576 | 100  | 0.0003        | -               |
+| 1.1364 | 150  | 0.0003        | -               |
+| 1.5152 | 200  | 0.0002        | -               |
+| 1.8939 | 250  | 0.0002        | -               |
+| 2.2727 | 300  | 0.0002        | -               |
+| 2.6515 | 350  | 0.0002        | -               |
 
 ### Framework Versions
 - Python: 3.11.7

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d7e6f700c77591393ea672121d1c9333f437786d8055fb4ca7a0518f772728
+oid sha256:a3f63e8fddef8a2fa2cb21b041e71e261097fe0df12c7600d1565c229f104491
 size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe4424288dd1f10f1153f922f56503bca8b1d5cbc81e15f79fa71ef66441708
+oid sha256:db132fe1e709899f490d56877ba55c99beef1b1644149db5e5fff26c4efdd390
 size 7007